Ok, thank you.
In the moment i am trying it with the standard "reg" command, like:
*-------------------- begin example ---------------
sysuse nlsw88, clear
gen ttl_exp2 = ttl_exp^2
gen wage_log = ln(wage)
reg wage ttl_exp ttl_exp2 grade
*--------------------- end example ----------------
At first, I calculate the logarithm of the wage because i want to
minimize anomalies.
A multivariate analysis via odd ratios is then a better resolution, i
presume, or?
2008/10/29, Maarten buis <[email protected]>:
> --- bumbuminc <[email protected]> wrote:
>
>> I mean
>>
>> Badi Baltagi wrote 2002 in "Econometrics" Page 84: In the
>> multivariate analyses,the variable wage per hour are a log function.
>> With these semi-log regression, the coefficient can in an exponential
>> equation [exp(b)-1] interpret the covariate over the dependent
>> variable as an percental effect.
>
> In the example I gave you earlier you will be able to make a statement
> like the the hourly wage changes by a factor of 1.08 for a year
> increase in education. This, obviously implies an 8% increase. In my
> particular sub-sub-discipline people are used to interpreting odds
> ratios, which have a very similar "factor change" interpretation, so I
> won't bother with subtracting 1, and multiplying by 100. Whether that
> works in your sub-sub-discipline is up to you.
>
> -- Maarten
>
> -----------------------------------------
> Maarten L. Buis
> Department of Social Research Methodology
> Vrije Universiteit Amsterdam
> Boelelaan 1081
> 1081 HV Amsterdam
> The Netherlands
>
> visiting address:
> Buitenveldertselaan 3 (Metropolitan), room N515
>
> +31 20 5986715
>
> http://home.fsw.vu.nl/m.buis/
> -----------------------------------------
>
>
>
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
>
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
